© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 194926
    Prev
    Next
    INDEX
    Explanations

    estimates that, new interfaces, please use

    np_acts-logits-general · gemini-2.5-flash-lite

    plot, chart, image, list, developing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.59
     удобно
    0.54
    Ꮕ
    0.54
    Imidazole
    0.50
     剤
    0.50
    YOUR
    0.50
    pFile
    0.49
     группа
    0.48
    Ihr
    0.47
     чле
    0.47
    POSITIVE LOGITS
     season
    0.51
     road
    0.50
     Spent
    0.49
     MSA
    0.48
     Faced
    0.47
     breakup
    0.47
    ವಹ
    0.47
     Prom
    0.46
    름
    0.46
     forced
    0.46
    Activations Density 0.000%

    No Known Activations